AutoML Leaderboard
AutoML Performance

AutoML Performance Boxplot

Features Importance

Spearman Correlation of Models

Summary of 5_Default_NeuralNetwork
<< Go back
Neural Network
- n_jobs: -1
- dense_1_size: 32
- dense_2_size: 16
- learning_rate: 0.05
- explain_level: 2
Validation
- validation_type: split
- train_ratio: 0.75
- shuffle: True
- stratify: True
Optimized metric
auc
Training time
1.5 seconds
Metric details
|
score |
threshold |
| logloss |
0.728984 |
nan |
| auc |
0.604687 |
nan |
| f1 |
0.651748 |
0.0937592 |
| accuracy |
0.582 |
0.517806 |
| precision |
0.693878 |
0.716811 |
| recall |
1 |
0.0071289 |
| mcc |
0.172976 |
0.313494 |
Metric details with threshold from accuracy metric
|
score |
threshold |
| logloss |
0.728984 |
nan |
| auc |
0.604687 |
nan |
| f1 |
0.490244 |
0.517806 |
| accuracy |
0.582 |
0.517806 |
| precision |
0.596439 |
0.517806 |
| recall |
0.416149 |
0.517806 |
| mcc |
0.161846 |
0.517806 |
Confusion matrix (at threshold=0.517806)
|
Predicted as 0 |
Predicted as 1 |
| Labeled as 0 |
381 |
136 |
| Labeled as 1 |
282 |
201 |
Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

<< Go back
Summary of 1_Baseline
<< Go back
Baseline Classifier (Baseline)
- n_jobs: -1
- explain_level: 2
Validation
- validation_type: split
- train_ratio: 0.75
- shuffle: True
- stratify: True
Optimized metric
auc
Training time
0.2 seconds
Metric details
|
score |
threshold |
| logloss |
0.692569 |
nan |
| auc |
0.5 |
nan |
| f1 |
0.651382 |
0.435 |
| accuracy |
0.483 |
0.435 |
| precision |
0.483 |
0.435 |
| recall |
1 |
0.435 |
| mcc |
0 |
0.435 |
Metric details with threshold from accuracy metric
|
score |
threshold |
| logloss |
0.692569 |
nan |
| auc |
0.5 |
nan |
| f1 |
0.651382 |
0.435 |
| accuracy |
0.483 |
0.435 |
| precision |
0.483 |
0.435 |
| recall |
1 |
0.435 |
| mcc |
0 |
0.435 |
Confusion matrix (at threshold=0.435)
|
Predicted as 0 |
Predicted as 1 |
| Labeled as 0 |
0 |
517 |
| Labeled as 1 |
0 |
483 |
Learning curves

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

<< Go back
Summary of Ensemble
<< Go back
Ensemble structure
| Model |
Weight |
| 3_Linear |
3 |
| 4_Default_Xgboost |
1 |
Metric details
|
score |
threshold |
| logloss |
0.665976 |
nan |
| auc |
0.634217 |
nan |
| f1 |
0.663205 |
0.318661 |
| accuracy |
0.598 |
0.562257 |
| precision |
0.85 |
0.759777 |
| recall |
1 |
0.100798 |
| mcc |
0.202265 |
0.423461 |
Metric details with threshold from accuracy metric
|
score |
threshold |
| logloss |
0.665976 |
nan |
| auc |
0.634217 |
nan |
| f1 |
0.491139 |
0.562257 |
| accuracy |
0.598 |
0.562257 |
| precision |
0.631922 |
0.562257 |
| recall |
0.401656 |
0.562257 |
| mcc |
0.198355 |
0.562257 |
Confusion matrix (at threshold=0.562257)
|
Predicted as 0 |
Predicted as 1 |
| Labeled as 0 |
404 |
113 |
| Labeled as 1 |
289 |
194 |
Learning curves

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

<< Go back
Summary of 2_DecisionTree
<< Go back
Decision Tree
- n_jobs: -1
- criterion: gini
- max_depth: 3
- explain_level: 2
Validation
- validation_type: split
- train_ratio: 0.75
- shuffle: True
- stratify: True
Optimized metric
auc
Training time
5.7 seconds
Metric details
|
score |
threshold |
| logloss |
0.703887 |
nan |
| auc |
0.502156 |
nan |
| f1 |
0.651382 |
0.331967 |
| accuracy |
0.519 |
0.59996 |
| precision |
0.522727 |
0.59996 |
| recall |
1 |
0.331967 |
| mcc |
0.0349949 |
0.368852 |
Metric details with threshold from accuracy metric
|
score |
threshold |
| logloss |
0.703887 |
nan |
| auc |
0.502156 |
nan |
| f1 |
0.0872865 |
0.59996 |
| accuracy |
0.519 |
0.59996 |
| precision |
0.522727 |
0.59996 |
| recall |
0.047619 |
0.59996 |
| mcc |
0.0170556 |
0.59996 |
Confusion matrix (at threshold=0.59996)
|
Predicted as 0 |
Predicted as 1 |
| Labeled as 0 |
496 |
21 |
| Labeled as 1 |
460 |
23 |
Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

<< Go back
Summary of 6_Default_RandomForest
<< Go back
Random Forest
- n_jobs: -1
- criterion: gini
- max_features: 0.9
- min_samples_split: 30
- max_depth: 4
- eval_metric_name: auc
- explain_level: 2
Validation
- validation_type: split
- train_ratio: 0.75
- shuffle: True
- stratify: True
Optimized metric
auc
Training time
5.2 seconds
Metric details
|
score |
threshold |
| logloss |
0.683715 |
nan |
| auc |
0.578397 |
nan |
| f1 |
0.651994 |
0.395058 |
| accuracy |
0.573 |
0.474979 |
| precision |
0.6 |
0.566713 |
| recall |
1 |
0.300369 |
| mcc |
0.151472 |
0.474979 |
Metric details with threshold from accuracy metric
|
score |
threshold |
| logloss |
0.683715 |
nan |
| auc |
0.578397 |
nan |
| f1 |
0.591388 |
0.474979 |
| accuracy |
0.573 |
0.474979 |
| precision |
0.549822 |
0.474979 |
| recall |
0.639752 |
0.474979 |
| mcc |
0.151472 |
0.474979 |
Confusion matrix (at threshold=0.474979)
|
Predicted as 0 |
Predicted as 1 |
| Labeled as 0 |
264 |
253 |
| Labeled as 1 |
174 |
309 |
Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

<< Go back
Summary of 4_Default_Xgboost
<< Go back
Extreme Gradient Boosting (Xgboost)
- n_jobs: -1
- objective: binary:logistic
- eta: 0.075
- max_depth: 6
- min_child_weight: 1
- subsample: 1.0
- colsample_bytree: 1.0
- eval_metric: auc
- explain_level: 2
Validation
- validation_type: split
- train_ratio: 0.75
- shuffle: True
- stratify: True
Optimized metric
auc
Training time
19.4 seconds
Metric details
|
score |
threshold |
| logloss |
0.67694 |
nan |
| auc |
0.613589 |
nan |
| f1 |
0.651382 |
0.103189 |
| accuracy |
0.597 |
0.510386 |
| precision |
0.826087 |
0.731419 |
| recall |
1 |
0.103189 |
| mcc |
0.191162 |
0.510386 |
Metric details with threshold from accuracy metric
|
score |
threshold |
| logloss |
0.67694 |
nan |
| auc |
0.613589 |
nan |
| f1 |
0.555678 |
0.510386 |
| accuracy |
0.597 |
0.510386 |
| precision |
0.59434 |
0.510386 |
| recall |
0.521739 |
0.510386 |
| mcc |
0.191162 |
0.510386 |
Confusion matrix (at threshold=0.510386)
|
Predicted as 0 |
Predicted as 1 |
| Labeled as 0 |
345 |
172 |
| Labeled as 1 |
231 |
252 |
Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

<< Go back
Summary of 3_Linear
<< Go back
Logistic Regression (Linear)
- n_jobs: -1
- explain_level: 2
Validation
- validation_type: split
- train_ratio: 0.75
- shuffle: True
- stratify: True
Optimized metric
auc
Training time
4.1 seconds
Metric details
|
score |
threshold |
| logloss |
0.669239 |
nan |
| auc |
0.631282 |
nan |
| f1 |
0.657728 |
0.246618 |
| accuracy |
0.6 |
0.534127 |
| precision |
0.8 |
0.800797 |
| recall |
1 |
0.0914683 |
| mcc |
0.19974 |
0.390411 |
Metric details with threshold from accuracy metric
|
score |
threshold |
| logloss |
0.669239 |
nan |
| auc |
0.631282 |
nan |
| f1 |
0.531616 |
0.534127 |
| accuracy |
0.6 |
0.534127 |
| precision |
0.61186 |
0.534127 |
| recall |
0.469979 |
0.534127 |
| mcc |
0.198043 |
0.534127 |
Confusion matrix (at threshold=0.534127)
|
Predicted as 0 |
Predicted as 1 |
| Labeled as 0 |
373 |
144 |
| Labeled as 1 |
256 |
227 |
Learning curves

Coefficients
| feature |
Learner_1 |
| feature_35 |
0.200405 |
| feature_20 |
0.192239 |
| feature_15 |
0.191565 |
| intercept |
0.146226 |
| feature_40 |
0.138789 |
| feature_33 |
0.135812 |
| feature_43 |
0.134685 |
| feature_66 |
0.130875 |
| feature_4 |
0.130841 |
| feature_12 |
0.126476 |
| feature_10 |
0.119604 |
| feature_49 |
0.118894 |
| feature_14 |
0.107123 |
| feature_19 |
0.104659 |
| feature_46 |
0.0949958 |
| feature_58 |
0.0940737 |
| feature_71 |
0.0897494 |
| feature_53 |
0.0893205 |
| feature_68 |
0.0839031 |
| feature_42 |
0.0813232 |
| feature_25 |
0.0804899 |
| feature_69 |
0.0795484 |
| feature_2 |
0.0768902 |
| feature_73 |
0.0739344 |
| feature_22 |
0.0732772 |
| feature_21 |
0.0710029 |
| feature_39 |
0.0676263 |
| feature_54 |
0.0670369 |
| feature_36 |
0.0655498 |
| feature_16 |
0.0655498 |
| feature_63 |
0.0621283 |
| feature_32 |
0.0602608 |
| feature_44 |
0.0571233 |
| feature_41 |
0.0553329 |
| feature_24 |
0.0404095 |
| feature_56 |
0.0297897 |
| feature_17 |
0.0272678 |
| feature_23 |
0.0191304 |
| feature_3 |
-0.00117303 |
| feature_27 |
-0.0141339 |
| feature_18 |
-0.0175461 |
| feature_38 |
-0.0220414 |
| feature_8 |
-0.028008 |
| feature_62 |
-0.0331552 |
| feature_76 |
-0.0389717 |
| feature_51 |
-0.0448625 |
| feature_13 |
-0.047958 |
| feature_50 |
-0.0490565 |
| feature_75 |
-0.0547078 |
| feature_74 |
-0.0570883 |
| feature_31 |
-0.059011 |
| feature_52 |
-0.0665689 |
| feature_61 |
-0.0693664 |
| feature_47 |
-0.0745467 |
| feature_7 |
-0.0761572 |
| feature_72 |
-0.0790566 |
| feature_1 |
-0.0802046 |
| feature_26 |
-0.0817932 |
| feature_65 |
-0.0830271 |
| feature_59 |
-0.0879831 |
| feature_48 |
-0.0910561 |
| feature_34 |
-0.0992595 |
| feature_28 |
-0.102777 |
| feature_30 |
-0.103224 |
| feature_45 |
-0.116688 |
| feature_64 |
-0.117451 |
| feature_37 |
-0.118839 |
| feature_67 |
-0.123572 |
| feature_11 |
-0.13637 |
| feature_55 |
-0.138853 |
| feature_57 |
-0.172999 |
| feature_9 |
-0.203542 |
| feature_29 |
-0.206588 |
| feature_5 |
-0.21696 |
| feature_70 |
-0.22905 |
| feature_6 |
-0.234133 |
| feature_60 |
-0.241553 |
Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

SHAP Dependence plots
Dependence (Fold 1)

SHAP Decision plots
Top-10 Worst decisions for class 0 (Fold 1)

Top-10 Best decisions for class 0 (Fold 1)

Top-10 Worst decisions for class 1 (Fold 1)

Top-10 Best decisions for class 1 (Fold 1)

<< Go back